Qwen3.7 Plus Is Now Available in Puter.js

Alibaba's Qwen team just released Qwen3.7 Plus, their multimodal agent model — and it's available to use through Puter.js.

What is Qwen3.7 Plus?

Qwen3.7 Plus is Alibaba's multimodal agent model, combining vision-language understanding with full agentic capabilities across a 1 million-token context window. Where the text-only Qwen3.7 Max is built for long-horizon text and coding, Plus adds eyes — it ingests images and video alongside text, processed through early-fusion training so vision and language are jointly understood from the first layer. Highlights include:

• Multimodal Inputs: Accepts text, images, and video in a single request, enabling screen perception, document understanding, and visual reasoning
• Frontier GUI Grounding: Scores 79.0 on ScreenSpot Pro — interpreting screenshots and pinpointing exactly where to click, placing it in the same tier as Claude Computer Use and OpenAI Operator
• 1M Token Context Window: Process entire codebases, lengthy documents, or long agent traces in a single request
• 65K Output Tokens: Generate long-form responses, complete implementations, and detailed plans without truncation
• Full Agentic Loop: Deep reasoning, self-programming, tool invocation, verification and testing, and autonomous iteration — the model writes and tests code, calls external APIs, and loops until the task is done
• Native Tool Use: Function calling and tool use out of the box, making it well-suited for GUI automation, browser/desktop agents, and end-to-end pipelines that combine seeing, reasoning, and doing

Choose Qwen3.7 Plus over Qwen3.7 Max when your workflow requires image or video inputs, browser/desktop automation, or agentic pipelines that need to see as well as reason.

Examples

Visual reasoning over a screenshot

puter.ai.chat("What's the next button I should click to complete checkout?", "https://example.com/cart-screenshot.png",
  { model: 'qwen/qwen3.7-plus' }
);

Multimodal agentic coding

puter.ai.chat("Here's a screenshot of the design mockup. Build a pixel-accurate React component to match it, then write tests for it", "https://example.com/mockup.png",
  { model: 'qwen/qwen3.7-plus' }
);

Document and chart understanding

puter.ai.chat("Extract every figure from this financial chart and return them as a structured JSON table", "https://example.com/revenue-chart.png",
  { model: 'qwen/qwen3.7-plus' }
);

Streaming with chain-of-thought reasoning

const response = await puter.ai.chat(
  "Plan a multi-step browser automation that books a flight, walking through each click and the trade-offs",
  { model: 'qwen/qwen3.7-plus', stream: true }
);

for await (const part of response) {
  if (part?.reasoning) puter.print(part?.reasoning);
  else puter.print(part?.text);
}

Get Started Now

Just add one library to your project:

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

Or add one script tag to your HTML:

<script src="https://js.puter.com/v2/"></script>

No API keys needed. Start building with Qwen3.7 Plus immediately.

Learn more:

• Free, Unlimited Qwen API
• Puter.js AI Documentation